Search result for: GPU
Page 2 / 2
Prev
| # | Post Title | Result Info | Date | User | Forum |
| RE: processing acceleration by CUDA / GPU | 12 Relevance | 3 years ago | Anonymous 174 | General | |
| Cuda won't be supported as it's system dependent. GPU support for more processing is something we want to implement, but that will be worked on at a later date. | |||||
| RE: State of GPU acceleration implementation? And also Star removal... | 12 Relevance | 4 years ago | Wouter van Reeven | General | |
| @digug Hi George, Currently APP 2.0.0 is in preparation which focuses on saving settings and intermediate processing state, as well as an extensive user manual. GPU acceleration is on the TODO list but not for this version. Why do you insist on having that? There is a Star Reduction tool that allows for reducing the star sizes and in some cases removing the stars completely. It works in a similar way as the other tools that you mention but is a custom implementation and doesn't allow yet to separate the stars, process them separately and recombine again. That, too, is planned for a future version of APP. HTH, Wouter | |||||
| RE: GPU is not being utilized | 12 Relevance | 4 years ago | Anonymous 174 | General | |
| APP doesn't use GPU processing (yet), it's used for the image viewer only at the moment. | |||||
| RE: Is there GPU rendering implemented yet? Considering an eGPU | 12 Relevance | 4 years ago | Anonymous 174 | General | |
| Sorry, impossible for me to judge. I know we want to start some small tests this year, but I really can't predict how that will go. I think, if you have a relatively decent GPU already, it will become faster anyway when supported. A good multi-code CPU is always nice to have also for APP. | |||||
| RE: M1 Native Support | 14 Relevance | 4 years ago | Jonathan Kimmitt | Apple MacOS | |
| I don't know whether this comparison is quite fair, GPU operations are very efficient for a certain class of operation, for example applying the same transformation to multiple blocks of an image in parallel with no dependency from the result of one operation to the input of the next, but a lot of algorithms are not like that and APP probably falls into the latter category for many of its functions, in fact to make a sweeping statement the majority of traditional CPU algorithms are not suitable for GPU, whereas any GPU algorithm can run on a CPU at lower thr ... | |||||
| RE: Something going wrong with my Mosaics | 14 Relevance | 4 years ago | Wouter van Reeven | General | |
| If you enable MBB (multi band blending) in tab 6 and increase to 10 or maybe even 15% then that should be much less visible. I'm sorry, what is the question exactly? Is the question perhaps "why isn't the GPU used"? To my best of knowledge, this isn't supported yet and will be in a future version of APP. | |||||
| RE: New M1 64gb MAX vs Original 16gb M1 Macbook Pro | 14 Relevance | 4 years ago | rixon | Apple MacOS | |
| ... 2TB SSD, 10 cores CPU, 32 cores GPU, with 400 GBps memory bandwidth. It has has 8 high performance cores and 2 high efficiency CPU cores. I'm not sure how OpenGL translates to Apple's metal graphics GPU usage and thus don't know if the 32 cores of GPU are being used at all by APP. Could you shed some light on that? Also, is there a formula to use when figuring how much RAM is necessary so that large mosaics don't downsize during integration? Thanks! | |||||
| RE: New Mac setup - Vulkan & Metal (MacOS) APIs | 14 Relevance | 6 years ago | Anonymous 174 | Apple MacOS | |
| Well, that's already a nice setup so those sub exposures are large indeed. Basically it's all about the amount of cores, memory, disk speed and definitely for the future a nice GPU. I would advice to go for a desktop if possible as these tend to be cheaper in comparison to raw performance (and still have better performance overall anyway). The new Threadripper CPU's from AMD are amazing for this, then a nice M.2 SSD directly on your motherboard for the processing part, as much memory as you can put in and a good GPU. Basically any GPU would already give a sp ... | |||||
| New Mac setup - Vulkan & Metal (MacOS) APIs | 14 Relevance | 6 years ago | Roy Salisbury | Apple MacOS | |
| I am looking to get a new system soon and want to make sure that I get something that APP can take full advantage of. I'll be processing some very large subexposures (122MB from the ASI6200 Color and Mono). I would assume LOTS of memory, and LOTS of cores, but what about the GPU? Or if I have a good GPU, can I get fewer processing cores? How is the Vulkan & Metal (MacOS) API work related to this? Right now I have a 4.2 Ghz i7 with 32G RAM and Radeon Pro 580 (8GB), and it will take pretty about 7 or 8 hours to fully process about 200 subs (5 nights). ... | |||||
| RE: GPU processing question - compute cards vs graphics cards | 12 Relevance | 4 years ago | Anonymous 174 | General | |
| We're not there yet, so I can't give details on different types of cards being an advantage or not to have. When APP has Vulkan support (which is still down the road) it will be able to use GPU's to calculate and that should be quite a bit faster. In the current landscape of graphics cards, I wouldn't spend top dollars on one just yet. | |||||
| RE: Is there GPU rendering implemented yet? Considering an eGPU | 12 Relevance | 5 years ago | Roman Kemord | General | |
| @vincent-modCheck this link: Starnet works very fast with CUDA but your program runs slowly with CPU.It would be good if you could make support for GPU available, as it would greatly improve the program's speed and user comfort. | |||||
| RE: Question on GPU processing | 12 Relevance | 6 years ago | Lammertus | General | |
| Thanks Vincent, I know it is hard to foresee! Is there some timeframe for the release of APP with GPU processing implemented? Stay well, Mert | |||||
| RE: Use GPU for heavy graphical calculations | 12 Relevance | 6 years ago | tschuh | RFCs - Request for changes | |
| It is certainly a major undertaking! I've played with CUDA a little bit and it takes SIGNIFICANT planning to get to a place where you can start throwing work units at the GPU. Can. Not. Wait! | |||||
| RE: Use GPU for heavy graphical calculations | 12 Relevance | 6 years ago | Anonymous 174 | RFCs - Request for changes | |
| Not yet, it will be when APP gets support for Vulkan which Mabula is working on. It is a big feature though so that will take time still. Maybe it's also an idea to look at desktops? They are usually cheaper and more powerful, a nice desktop GPU will then help a lot when Vulkan is supported. | |||||
| RE: Integration speed seems slow | 14 Relevance | 8 years ago | Mabula-Admin | General | |
| ... capabilities with the processing sliders on the right side. For simple calculations, the GPUs won't be that effective, they really excel with difficult calculations. However I think that the amount of calculation units of current graphics cards dwarf the amount of cpu cores availble in most systems... 😉 Current graphics cards have over 1000 calculation units... I am planning for an implementation in certain modules, that will use GPU and/or CPU if available and only CPU otherwise. So with a switchbox in the CFG menu, you will be able to turn on/off GPU su ... | |||||
| RE: State of GPU acceleration implementation? And also Star removal... | 12 Relevance | 3 years ago | outer space | General | |
| @jc130676 & @digug My two cents here is that, typically, Neural network models benefit a lot from GPU acceleration. GPUs perform matrix transforms with very large number of parallel operations and quickly. Matrix transforms depend wholly on multiply-and-accumulate operations that are super optimized in GPUs. AFAIK (and I am not part of the dev team), APP probably does have a lot of signal processing steps and transforms that may not be readily available with standard CUDA libraries (required for NVIDIA GPUs) so development and optimization for sp ... | |||||
Page 2 / 2
Prev
